Hi everyone, is the same as this post title. Our partners and I have established a bioinformatics algorithm competition to promote the attention and development of spatial transcriptomics and solicit new methods for multi-modal data and multi-omics data analysis.
[This is not a commercial. The entire contest is for public benefit.]
It names: 2024 Mammoth International Contest On Omics Sciences in Europe (MICOS-EU)
For this competition, we have sought prizes of more than 20,000 USD from our partners to reward outstanding contestants, and the winners will also have the opportunity to receive a full scholarship.
We all know that Spatial Transcriptomics was named the 2020 Method of the Year by Nature Methods because of its enormous value to the big data analysis of multi-omics data.
It plays a crucial role in a multitude of applications to omics research and data science by providing spatially resolved gene expression information within tissues or organisms. This technology enables the integration of transcriptomic data with other omics data, such as genomics, proteomics, and metabolomics, and combines images and video data for correlation to gain a comprehensive understanding of biological systems.
The high dimensionality, heterogeneity, complementarity, and consistency of multi-omics datasets (including spatial transcriptomics data) present challenges for data analysis.
Therefore, we hope to utilize clustering algorithms to optimize and integrate spatial transcriptomics data to enhance the effectiveness and interpretability of data analysis.
We welcome all researchers to participate to promote the use of data and the advancement of algorithms.
Youtube Video for MICOS-EU introduction:
Micos-EU website: https://micos.cngb.org/europe/
Contest platform: https://www.datacontest.net/v3/cmptDetail.html?id=878
Contest question details:
To effectively address the accuracy and efficiency issues of clustering algorithms used for spatial transcriptomics data, the organizers will provide participants with spatial transcriptomic gene expression data in ".gem.gz" format , raw HE images, and cell segmentation mask files . Participants are expected to apply/improve/develop preprocessing and clustering algorithms suitable for integrating transcriptomic data and HE image data, while ensuring the accuracy of the analysis results. The goal is to reduce computational memory consumption of the algorithms and improve computational speed. The achievement of the objective will be determined by the spatial visualization of the clustering results and relevant evaluation metrics.
Contest Dataset: https://db.cngb.org/stomics/datasets/STDS0000240